Internet radio browser GUI for music/video streams from various directory services.

โŒˆโŒ‹ โŽ‡ branch:  streamtuner2


Check-in [72806f95a5]

Overview
Comment:Document channel website behaviour / internal playlist generation urls. Reuse global conf.max_streams (as orientation for no of pages to fetch).
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1:72806f95a533881fce09abf96bdf492e0b46e18f
User & Date: mario on 2017-02-13 16:50:28
Other Links: manifest | tags
Context
2017-02-13
16:51
Add -V cmdline arg. check-in: becb24c89e user: mario tags: trunk
16:50
Document channel website behaviour / internal playlist generation urls. Reuse global conf.max_streams (as orientation for no of pages to fetch). check-in: 72806f95a5 user: mario tags: trunk
16:48
Simplify best_url() dict generation, typecasting, add more comments on channel webpage. check-in: c05cee4440 user: mario tags: trunk
Changes

Modified contrib/streamlicensing.py from [b6646ebe43] to [5b03ee0a9c].

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

















32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52


53
54
55
56
57

58
59
60
61
62
63
64
..
66
67
68
69
70
71
72

73
74
75
76
77
78
79
80
81
82
83
84
# encoding: UTF-8
# api: streamtuner2
# title: streamlicensing
# description: Smaller streaming service provider
# url: http://www.streamlicensing.com/directory/
# version: 0.1
# type: channel
# category: radio
# priority: extra
# png:
#   iVBORw0KGgoAAAANSUhEUgAAABAAAAAQBAMAAADt3eJSAAAAGFBMVEVhcAAODy8rLVpHS4RPU22DismUmLTm6va3Zc/ZAAAAAXRSTlMAQObYZgAA
#   AAFiS0dEAIgFHUgAAAAJcEhZcwAACxMAAAsTAQCanBgAAAAHdElNRQfhAgwUMiN14qDwAAAAW0lEQVQI12NggAADCMVW7gym3crBDJb08rJgZbB4
#   qqEQmBGsKMQEZggqMLCA1LAJM8AZaWUQhjpEO5uwamiQMJjBrChkADSlXBhsfHh5qgCYoWysqACxWQlCAwArBw5QNfhFygAAAABJRU5ErkJggg==
# extraction-method: regex
#
# Streaming service provider, which ensures station legality or fees
# according to US copyright/streaming laws.
#
# Has only major categories. Does not provide channel homepages, and
# is a bit slow due to huge page sizes. No search function implemented
# here.
#


import re
import ahttp
from config import *
from channels import *


# radiolist.net

















class streamlicensing (ChannelPlugin):

    # module attributes
    listformat = "pls"
    has_search = False
    categories = []
    catmap = {}
    titles = dict( listeners=False )
    
    # config (not as plugin options here)
    conf_family_unsafe = 0
    conf_maxpages = 3
    
    # magic values
    base_url = "http://www.streamlicensing.com/directory/"
    pls_sffx = "%sindex.cgi/playlist.pls?action=playlist&type=pls&sid=%s&stream_id=%s"
    # This is well hidden, but it comes with a playlist generator, so doesn't require double lookups.
    # http://www.streamlicensing.com/directory/index.cgi?action=webpro_links&sid=4785&start=1&g=14&e=1&s=
    # .../directory/index.cgi/playlist.pls?action=playlist&type=pls&sid=4785&stream_id=1234

    # just a static list for now


    def update_categories(self):
        html = ahttp.get(self.base_url)
        cats = re.findall('"\?start=&g=(\d+)&e=&s="><.+?>([\w\s-]+)</span>', html)
        self.categories = sorted([c[1] for c in cats])
        self.catmap = dict([(t,i) for i,t in cats])


    # extract stream urls
    def update_streams(self, cat):
    
        # prep block regex
        rx_genre = re.compile(r"""
           <tr\sid='(\d+)' .*?
................................................................................
           ^var\slastsong_\d+\s*=\s*'([^\n]+)'; .*?
           <a[^>]+onClick=[^>]+&stream_id=(\d+)'[^>]+>(\d+)k<
        """, re.I|re.S|re.X|re.M)
        
        # collect pages into single string
        html = ""
        for page in range(0, self.conf_maxpages):

            html += ahttp.get("%s?start=%s&g=%s&e=%s&s=" % (self.base_url, page * 10, self.catmap[cat], self.conf_family_unsafe))
            if not re.search("\?start=%s.*>Next" % ((page + 1) * 10), html):
                break
        html = re.sub(">Featured Stations.+?>Previous Page", "", html, 100, re.S)
        print html

        # extract and convert to station rows
        entries = []
        for uu in re.findall(rx_genre, html):
            print uu
            entries.append(dict(
                genre = cat,





|









|
|













|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>











|




<
<
<

<
>
>





>







 







>




<







1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64



65

66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
..
82
83
84
85
86
87
88
89
90
91
92
93

94
95
96
97
98
99
100
# encoding: UTF-8
# api: streamtuner2
# title: streamlicensing
# description: Smaller streaming service provider
# url: http://www.streamlicensing.com/directory/
# version: 0.2
# type: channel
# category: radio
# priority: extra
# png:
#   iVBORw0KGgoAAAANSUhEUgAAABAAAAAQBAMAAADt3eJSAAAAGFBMVEVhcAAODy8rLVpHS4RPU22DismUmLTm6va3Zc/ZAAAAAXRSTlMAQObYZgAA
#   AAFiS0dEAIgFHUgAAAAJcEhZcwAACxMAAAsTAQCanBgAAAAHdElNRQfhAgwUMiN14qDwAAAAW0lEQVQI12NggAADCMVW7gym3crBDJb08rJgZbB4
#   qqEQmBGsKMQEZggqMLCA1LAJM8AZaWUQhjpEO5uwamiQMJjBrChkADSlXBhsfHh5qgCYoWysqACxWQlCAwArBw5QNfhFygAAAABJRU5ErkJggg==
# extraction-method: regex
#
# Streaming service provider, which ensures station legality and fees
# in accordance with US copyright conversion corporations.
#
# Has only major categories. Does not provide channel homepages, and
# is a bit slow due to huge page sizes. No search function implemented
# here.
#


import re
import ahttp
from config import *
from channels import *


# streamlicensing.com
#
# ยท Provides around 20 categories, associated to numeric ids (?g= parameter)
#
# ยท Station lists are one <tr> block each, with a JS inline script associating
#   some web player parameters.
#
# ยท Each station has a station id=, but also a stream_id= for the playlist
#   generator.
#
# ยท Normally just provides a web player, but used to show .pls links for various
#   players. Meanwhile this is hidden, but the playlist generator is still
#   available - so doesn't require double lookups.
#   โ†’ http://www.streamlicensing.com/directory/index.cgi?action=webpro_links&sid=4785&start=1&g=14&e=1&s=
#   โ†’ .../directory/index.cgi/playlist.pls?action=playlist&type=pls&sid=4785&stream_id=1234
#
# ยท family_safe and maxpages are hardcoded config options for now.
#
class streamlicensing (ChannelPlugin):

    # module attributes
    listformat = "pls"
    has_search = False
    categories = []
    catmap = {}
    titles = dict( listeners=False )
    
    # config (not as plugin options here)
    conf_family_unsafe = 0
    conf_maxpages = max(int(int(conf.max_streams) / 100), 1)
    
    # magic values
    base_url = "http://www.streamlicensing.com/directory/"
    pls_sffx = "%sindex.cgi/playlist.pls?action=playlist&type=pls&sid=%s&stream_id=%s"






    # fetch category titles and catmap
    def update_categories(self):
        html = ahttp.get(self.base_url)
        cats = re.findall('"\?start=&g=(\d+)&e=&s="><.+?>([\w\s-]+)</span>', html)
        self.categories = sorted([c[1] for c in cats])
        self.catmap = dict([(t,i) for i,t in cats])


    # extract stream urls
    def update_streams(self, cat):
    
        # prep block regex
        rx_genre = re.compile(r"""
           <tr\sid='(\d+)' .*?
................................................................................
           ^var\slastsong_\d+\s*=\s*'([^\n]+)'; .*?
           <a[^>]+onClick=[^>]+&stream_id=(\d+)'[^>]+>(\d+)k<
        """, re.I|re.S|re.X|re.M)
        
        # collect pages into single string
        html = ""
        for page in range(0, self.conf_maxpages):
            self.progress(self.conf_maxpages, page)
            html += ahttp.get("%s?start=%s&g=%s&e=%s&s=" % (self.base_url, page * 10, self.catmap[cat], self.conf_family_unsafe))
            if not re.search("\?start=%s.*>Next" % ((page + 1) * 10), html):
                break
        html = re.sub(">Featured Stations.+?>Previous Page", "", html, 100, re.S)


        # extract and convert to station rows
        entries = []
        for uu in re.findall(rx_genre, html):
            print uu
            entries.append(dict(
                genre = cat,